{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:12:31Z","timestamp":1776489151435,"version":"3.51.2"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2022YFB3104703"],"award-info":[{"award-number":["2022YFB3104703"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172103"],"award-info":[{"award-number":["62172103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s11263-023-01880-0","type":"journal-article","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T08:07:33Z","timestamp":1693814853000},"page":"300-318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["CDistNet: Perceiving Multi-domain Character Distance for Robust Text Recognition"],"prefix":"10.1007","volume":"132","author":[{"given":"Tianlun","family":"Zheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1543-6889","authenticated-orcid":false,"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shancheng","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,4]]},"reference":[{"key":"1880_CR1","doi-asserted-by":"crossref","unstructured":"Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J., Lee, H. (2019). What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: ICCV (pp. 4714\u20134722).","DOI":"10.1109\/ICCV.2019.00481"},{"key":"1880_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., Matsui, Y., Aizawa, K. (2021). What if we only use real datasets for scene text recognition? toward scene text recognition with fewer labels. In: CVPR (pp. 3113\u20133122).","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"1880_CR3","doi-asserted-by":"crossref","unstructured":"Bai, J., Chen, Z., Feng, B., & Xu, B. (2014). Chinese image text recognition on grayscale pixels. 2014 IEEE International Conference on Acoustics (pp. 1380\u20131384). IEEE: Speech and Signal Processing (ICASSP).","DOI":"10.1109\/ICASSP.2014.6853823"},{"key":"1880_CR4","doi-asserted-by":"crossref","unstructured":"Bautista, D. & Atienza, R. (2022). Scene text recognition with permuted autoregressive sequence models. In: ECCV, Springer (pp. 178\u2013196).","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"1880_CR5","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Sain, A., Kumar, A., Ghose, S., Chowdhury, P.N. & Song, Y.Z. (2021). Joint visual semantic reasoning: Multi-stage decoder for text recognition. In: ICCV (pp. 14920\u201314929).","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"1880_CR6","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.neucom.2019.11.049","volume":"381","author":"X Chen","year":"2020","unstructured":"Chen, X., Wang, T., Zhu, Y., Jin, L., & Luo, C. (2020). Adaptive embedding gate for attention-based scene text recognition. Neurocomputing, 381, 261\u2013271.","journal-title":"Neurocomputing"},{"issue":"2","key":"1880_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3440756","volume":"54","author":"X Chen","year":"2021","unstructured":"Chen, X., Jin, L., Zhu, Y., Luo, C., & Wang, T. (2021). Text recognition in the wild: A survey. ACM Computing Surveys (CSUR), 54(2), 1\u201335.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"1880_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S. & Zhou, S. (2017). Focusing attention: Towards accurate text recognition in natural images. In: ICCV (pp. 5076\u20135084).","DOI":"10.1109\/ICCV.2017.543"},{"key":"1880_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S. & Zhou, S. (2018). Aon: Towards arbitrarily-oriented text recognition. In: CVPR (pp. 5571\u20135579).","DOI":"10.1109\/CVPR.2018.00584"},{"key":"1880_CR10","doi-asserted-by":"crossref","unstructured":"Chng, C.K., Liu, Y., Sun, Y., Ng, C.C., Luo, C., Ni, Z., Fang, C., Zhang, S., Han, J., Ding, E., et\u00a0al. (2019). Icdar2019 robust reading challenge on arbitrary-shaped text-RRC-ART. In: ICDAR, IEEE (pp. 1571\u20131576).","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"1880_CR11","doi-asserted-by":"crossref","unstructured":"Da, C., Wang, P. & Yao, C. (2022). Levenshtein ocr. In: ECCV, Springer (pp. 322\u2013338).","DOI":"10.1007\/978-3-031-19815-1_19"},{"key":"1880_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K. & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT"},{"key":"1880_CR13","doi-asserted-by":"crossref","unstructured":"Du, Y., Chen, Z., Jia, C., Yin, X., Zheng, T., Li, C., Du, Y. & Jiang, Y.G. (2022). SVTR: Scene text recognition with a single visual model. In: IJCAI (pp. 884\u2013890).","DOI":"10.24963\/ijcai.2022\/124"},{"key":"1880_CR14","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y. (2021). Read like humans: Autonomous, bidirectional and iterative language modeling for scene text recognition. In: CVPR (pp. 7094\u20137103).","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"1880_CR15","doi-asserted-by":"crossref","unstructured":"Fang, S., Mao, Z., Xie, H., Wang, Y., Yan, C., Zhang, Y. (2022). Abinet++: Autonomous, bidirectional and iterative language modeling for scene text spotting. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"1880_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A. & Zisserman, A. (2016) Synthetic data for text localisation in natural images. In: CVPR (pp. 2315\u20132324).","DOI":"10.1109\/CVPR.2016.254"},{"key":"1880_CR17","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C.C. & Tang, X. (2016). Reading scene text in deep convolutional sequences. In: AAAI (pp. 3501\u20133508).","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"1880_CR18","doi-asserted-by":"crossref","unstructured":"He, Y., Chen, C., Zhang, J., Liu, J., He, F., Wang, C. & Du, B. (2022). Visual semantics allow for textual reasoning better in scene text recognition. In: AAAI (pp. 888\u2013896).","DOI":"10.1609\/aaai.v36i1.19971"},{"key":"1880_CR19","doi-asserted-by":"publisher","first-page":"11005","DOI":"10.1609\/aaai.v34i07.6735","volume":"34","author":"W Hu","year":"2020","unstructured":"Hu, W., Cai, X., Hou, J., Yi, S., & Lin, Z. (2020). GTC: Guided training of CTC towards efficient and accurate scene text recognition. AAAI, 34, 11005\u201311012.","journal-title":"AAAI"},{"key":"1880_CR20","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A. & Zisserman, A. (2014). Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227"},{"issue":"1","key":"1880_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., & Zisserman, A. (2016). Reading text in the wild with convolutional neural networks. International Journal of Computer Vision, 116(1), 1\u201320.","journal-title":"International Journal of Computer Vision"},{"key":"1880_CR22","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., & Lu, S. (2015) ICDAR 2015 competition on robust reading. In: ICDAR (pp. 1156\u20131160).","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"1880_CR23","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942"},{"key":"1880_CR24","doi-asserted-by":"crossref","unstructured":"Lee, C.Y. & Osindero, S. (2016). Recursive recurrent nets with attention modeling for OCR in the wild. In: CVPR (pp. 2231\u20132239).","DOI":"10.1109\/CVPR.2016.245"},{"key":"1880_CR25","doi-asserted-by":"publisher","first-page":"8610","DOI":"10.1609\/aaai.v33i01.33018610","volume":"33","author":"H Li","year":"2019","unstructured":"Li, H., Wang, P., Shen, C., & Zhang, G. (2019). Show, attend and read: A simple and strong baseline for irregular text recognition. AAAI, 33, 8610\u20138617.","journal-title":"AAAI"},{"key":"1880_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., & Wei, Y. (2017). Fully convolutional instance-aware semantic segmentation. In: CVPR (pp. 2359\u20132367).","DOI":"10.1109\/CVPR.2017.472"},{"issue":"2","key":"1880_CR27","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TPAMI.2019.2937086","volume":"43","author":"M Liao","year":"2019","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., & Bai, X. (2019). Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(2), 532\u2013548.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1880_CR28","doi-asserted-by":"publisher","first-page":"8714","DOI":"10.1609\/aaai.v33i01.33018714","volume":"33","author":"M Liao","year":"2019","unstructured":"Liao, M., Zhang, J., Wan, Z., Xie, F., Liang, J., Lyu, P., Yao, C., & Bai, X. (2019). Scene text recognition from two-dimensional perspective. AAAI, 33, 8714\u20138721.","journal-title":"AAAI"},{"issue":"1","key":"1880_CR29","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., & Yao, C. (2021). Scene text detection and recognition: The deep learning era. International Journal of Computer Vision, 129(1), 161\u2013184.","journal-title":"International Journal of Computer Vision"},{"key":"1880_CR30","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo, C., Jin, L., & Sun, Z. (2019). MORAN: A multi-object rectified attention network for scene text recognition. Pattern Recognition, 90, 109\u2013118.","journal-title":"Pattern Recognition"},{"key":"1880_CR31","doi-asserted-by":"crossref","unstructured":"Luo, C., Zhu, Y., Jin, L., & Wang, Y. (2020). Learn to augment: Joint data augmentation and network optimization for text recognition. In: CVPR (pp. 13746\u201313755).","DOI":"10.1109\/CVPR42600.2020.01376"},{"issue":"4","key":"1880_CR32","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1007\/s11263-020-01411-1","volume":"129","author":"C Luo","year":"2021","unstructured":"Luo, C., Lin, Q., Liu, Y., Jin, L., & Shen, C. (2021). Separating content from style using adversarial learning for recognizing text in the wild. International Journal of Computer Vision, 129(4), 960\u2013976.","journal-title":"International Journal of Computer Vision"},{"key":"1880_CR33","doi-asserted-by":"crossref","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X. (2018). Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. In: ECCV (pp 67\u201383).","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"1880_CR34","unstructured":"Lyu, P., Yang, Z., Leng, X., Wu, X., Li, R., Shen, X. (2019). 2d attentional irregular scene text recognizer. arXiv preprint arXiv:1906.05708"},{"key":"1880_CR35","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., & Jawahar, C. (2012) Scene text recognition using higher order language priors. In: BMVC (pp. 1\u201311).","DOI":"10.5244\/C.26.127"},{"key":"1880_CR36","first-page":"1454","volume":"1","author":"N Nayef","year":"2017","unstructured":"Nayef, N., Yin, F., Bizid, I., Choi, H., Feng, Y., Karatzas, D., Luo, Z., Pal, U., Rigaud, C., & Chazalon, J. (2017). Icdar 2017 robust reading challenge on multi-lingual scene text detection and script identification-RRC-MLT. ICDAR, IEEE, 1, 1454\u20131459.","journal-title":"ICDAR, IEEE"},{"key":"1880_CR37","doi-asserted-by":"crossref","unstructured":"Nayef, N., Patel, Y., Busta, M., Chowdhury, P.N., Karatzas, D., Khlif, W., Matas, J., Pal, U., Burie, J.C., & Liu, C.l. et\u00a0al. (2019) Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019. In: ICDAR, IEEE (pp. 1582\u20131587).","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"1880_CR38","doi-asserted-by":"crossref","unstructured":"Nguyen, N., Nguyen, T., Tran, V., Tran, M.T., Ngo, T.D., Nguyen, T.H., & Hoai, M. (2021). Dictionary-guided scene text recognition. In: CVPR (pp. 7383\u20137392).","DOI":"10.1109\/CVPR46437.2021.00730"},{"issue":"11","key":"1880_CR39","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1007\/s11263-022-01654-0","volume":"130","author":"D Peng","year":"2022","unstructured":"Peng, D., Jin, L., Liu, Y., Luo, C., & Lai, S. (2022). Pagenet: Towards end-to-end weakly supervised page-level handwritten Chinese text recognition. International Journal of Computer Vision, 130(11), 2623\u20132645.","journal-title":"International Journal of Computer Vision"},{"key":"1880_CR40","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., & Tan, C.L. (2013) Recognizing text with perspective distortion in natural scenes. In: ICCV (pp. 569\u2013576).","DOI":"10.1109\/ICCV.2013.76"},{"key":"1880_CR41","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., & Wang, W. (2020) Seed: Semantics enhanced encoder-decoder framework for scene text recognition. In: CVPR (pp. 13525\u201313534).","DOI":"10.1109\/CVPR42600.2020.01354"},{"issue":"18","key":"1880_CR42","first-page":"8027","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan, A., Shivakumara, P., Chan, C. S., & Tan, C. L. (2014). A robust arbitrary text detection system for natural scene images. ESA, 41(18), 8027\u20138048.","journal-title":"ESA"},{"issue":"3","key":"1880_CR43","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s11263-014-0793-6","volume":"113","author":"JA Rodriguez-Serrano","year":"2015","unstructured":"Rodriguez-Serrano, J. A., Gordo, A., & Perronnin, F. (2015). Label embedding: A frugal baseline for text recognition. International Journal of Computer Vision, 113(3), 193\u2013207.","journal-title":"International Journal of Computer Vision"},{"key":"1880_CR44","doi-asserted-by":"crossref","unstructured":"Sheng, F., Chen, Z., & Xu, B. (2019) Nrtr: A no-recurrence sequence-to-sequence model for scene text recognition. In: ICDAR (pp. 781\u2013786).","DOI":"10.1109\/ICDAR.2019.00130"},{"issue":"11","key":"1880_CR45","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., & Yao, C. (2017). An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), 2298\u20132304.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"1880_CR46","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., & Bai, X. (2018). Aster: An attentional scene text recognizer with flexible rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(9), 2035\u20132048.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1880_CR47","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.patcog.2016.10.016","volume":"63","author":"B Su","year":"2017","unstructured":"Su, B., & Lu, S. (2017). Accurate recognition of words in scenes without character segmentation using recurrent neural network. Pattern Recognition, 63, 397\u2013405.","journal-title":"Pattern Recognition"},{"key":"1880_CR48","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L. & Polosukhin, I. (2017). Attention is all you need. In: NIPS (pp. 5998\u20136008)."},{"key":"1880_CR49","doi-asserted-by":"crossref","unstructured":"Wan, Z., He, M., Chen, H., Bai, X., & Yao, C. (2020). Textscanner: Reading characters in order for robust scene text recognition. AAAI, 34, 12120\u201312127.","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"1880_CR50","unstructured":"Wang, K., Babenko, B., & Belongie, S. (2011) End-to-end scene text recognition. In: ICCV (pp. 1457\u20131464)."},{"key":"1880_CR51","unstructured":"Wang, P., Yang, L., Li, H., Deng, Y., Shen, C. & Zhang, Y. (2019a). A simple and robust convolutional-attention network for irregular text recognition. arXiv preprint arXiv:1904.01375"},{"key":"1880_CR52","doi-asserted-by":"crossref","unstructured":"Wang, P., Da, C., & Yao, C. (2022a) Multi-granularity prediction for scene text recognition. In: ECCV, Springer (pp. 339\u2013355).","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"1880_CR53","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, Y., Qin, X., Zhao, Q., & Tang, Z. (2019b) Scene text recognition via gated cascade attention. In: ICME (pp. 1018\u20131023).","DOI":"10.1109\/ICME.2019.00179"},{"key":"1880_CR54","doi-asserted-by":"publisher","first-page":"12216","DOI":"10.1609\/aaai.v34i07.6903","volume":"34","author":"T Wang","year":"2020","unstructured":"Wang, T., Zhu, Y., Jin, L., Luo, C., Chen, X., Wu, Y., Wang, Q., & Cai, M. (2020). Decoupled attention network for text recognition. AAAI, 34, 12216\u201312224.","journal-title":"AAAI"},{"key":"1880_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y. (2021). From two to one: A new scene text recognizer with visual language modeling network. In: ICCV (pp. 14174\u201314183).","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"1880_CR56","doi-asserted-by":"publisher","first-page":"5585","DOI":"10.1109\/TIP.2022.3197981","volume":"31","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Xie, H., Fang, S., Xing, M., Wang, J., Zhu, S., & Zhang, Y. (2022). Petr: Rethinking the capability of transformer-based language model in scene text recognition. IEEE Transactions on Image Processing, 31, 5585\u20135598.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1880_CR57","doi-asserted-by":"crossref","unstructured":"Xie, X., Fu, L., Zhang, Z., Wang, Z., Bai, X. (2022). Toward understanding wordart: Corner-guided transformer for scene text recognition. In: ECCV, Springer (pp. 303\u2013321).","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"1880_CR58","doi-asserted-by":"crossref","unstructured":"Xing, L., Tian, Z., Huang, W. & Scott, M.R. (2019). Convolutional character networks. In: ICCV (pp. 9126\u20139136).","DOI":"10.1109\/ICCV.2019.00922"},{"key":"1880_CR59","doi-asserted-by":"crossref","unstructured":"Yan, R., Peng, L., Xiao, S. & Yao, G. (2021). Primitive representation learning for scene text recognition. In: CVPR (pp. 284\u2013293).","DOI":"10.1109\/CVPR46437.2021.00035"},{"issue":"7","key":"1880_CR60","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2014","unstructured":"Ye, Q., & Doermann, D. (2014). Text detection and recognition in imagery: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(7), 1480\u20131500.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1880_CR61","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., & Ding, E. (2020) Towards accurate scene text recognition with semantic reasoning networks. In: CVPR (pp. 12113\u201312122).","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"1880_CR62","doi-asserted-by":"crossref","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H. & Zhang, W. (2020) Robustscanner: Dynamically enhancing positional clues for robust text recognition. In: ECCV (pp. 135\u2013151)","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"1880_CR63","doi-asserted-by":"crossref","unstructured":"Zhan, F., & Lu, S. (2019) Esir: end-to-end scene text recognition via iterative image rectification. In: CVPR (pp. 2059\u20132068).","DOI":"10.1109\/CVPR.2019.00216"},{"key":"1880_CR64","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., & Kadlec, B. (2017). Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: SUNw: Scene Understanding Workshop-CVPR"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01880-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01880-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01880-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T07:13:26Z","timestamp":1706598806000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01880-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":64,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1880"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01880-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,4]]},"assertion":[{"value":"21 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}